© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 143456
    Prev
    Next
    INDEX
    Explanations

    therefore be, either gift, rise to, altar as, reach the

    np_acts-logits-general · gemini-2.5-flash-lite

    functioning optimally or fusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subtracted
    0.51
    accum
    0.48
    ācijas
    0.45
     शुक्ला
    0.45
     Gainesville
    0.45
    tuple
    0.44
    Crossing
    0.44
    r
    0.44
     vanished
    0.43
     freezed
    0.43
    POSITIVE LOGITS
     economico
    0.52
     systému
    0.51
     ressort
    0.50
     Sistema
    0.48
     piac
    0.47
     indiqu
    0.47
     territoriale
    0.47
     bölges
    0.46
     indiquer
    0.46
     sistemi
    0.46
    Activations Density 0.000%

    No Known Activations