© 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. 97722
    Prev
    Next
    INDEX
    Explanations

    introducing clauses or descriptions

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

    but there

    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
     strangle
    0.52
     lyric
    0.46
     calorimeter
    0.46
     dvs
    0.45
    軞
    0.45
     خ
    0.45
     crappy
    0.44
     média
    0.44
     bullshit
    0.43
     सिन्हा
    0.43
    POSITIVE LOGITS
    sa
    0.60
    ra
    0.58
    oma
    0.55
    ues
    0.53
    sim
    0.53
    error
    0.52
    raa
    0.52
    la
    0.51
    ran
    0.51
    ọ
    0.51
    Activations Density 0.000%

    No Known Activations