© 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. 32776
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and scores

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

    algebraic expressions with operators

    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
    ப்படுத்தும்
    0.43
    猗
    0.41
    왁
    0.41
     ٹرسٹ
    0.40
     نہيں
    0.40
    🗸
    0.40
    Mutability
    0.40
    福建
    0.40
    􀂃
    0.40
     চাহিল
    0.39
    POSITIVE LOGITS
     pourtant
    0.58
     nor
    0.55
    }=-
    0.48
    nor
    0.48
     blaming
    0.47
     blame
    0.46
     hateful
    0.46
    而是
    0.45
    💔
    0.44
     regres
    0.43
    Activations Density 0.007%

    No Known Activations