© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1976
    Prev
    Next
    INDEX
    Explanations

    common themes and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ಾಗಲೇ
    2.84
    ar
    2.52
    েম
    2.52
    }$.
    2.46
     canister
    2.45
    }),
    2.43
    }\
    2.39
    }$,
    2.39
     costas
    2.39
    },(
    2.36
    POSITIVE LOGITS
     xuyên
    3.40
     haunts
    3.07
     اوقات
    2.99
    ী
    2.90
    kali
    2.90
    currentUser
    2.88
     denominators
    2.84
    alities
    2.83
     corrientes
    2.79
     occurrence
    2.77
    Activations Density 0.826%

    No Known Activations