© 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. 78289
    Prev
    Next
    INDEX
    Explanations

    usually followed by nouns or durations

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

    without endorsing

    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
    ্যান
    0.48
     Rebels
    0.46
    𝐼
    0.45
    ליה
    0.45
    anku
    0.44
    góc
    0.44
    प्रा
    0.43
     Afterward
    0.43
    鋃
    0.43
     and
    0.43
    POSITIVE LOGITS
     whakap
    0.48
     warmer
    0.47
     situés
    0.45
     പഞ്ചായ
    0.45
    j
    0.44
     mobilise
    0.44
    同事
    0.44
    pOt
    0.44
     अभिकथन
    0.44
    PARATOR
    0.43
    Activations Density 0.000%

    No Known Activations