© 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. 166124
    Prev
    Next
    INDEX
    Explanations

    version for

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

    maximizes your payout

    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
     tristeza
    0.54
    ፍተኛ
    0.49
     Prisoner
    0.45
    شاعر
    0.45
    ظيف
    0.44
    shoes
    0.44
     posterity
    0.44
    냥
    0.43
     surtout
    0.43
    minded
    0.43
    POSITIVE LOGITS
    י
    0.49
    Ö
    0.44
    ブリ
    0.43
    AN
    0.43
    OMB
    0.42
    SON
    0.42
     juht
    0.41
    ATT
    0.41
     akt
    0.41
    たと
    0.40
    Activations Density 0.002%

    No Known Activations