© 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. 224570
    Prev
    Next
    INDEX
    Explanations

    necessary, URL, unpaid, the Divine, After, £, power, Vol

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

    OpenAI code

    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
    聸
    0.51
    䪱
    0.50
    顗
    0.50
    ুক্তি
    0.49
    缑
    0.46
     ديك
    0.45
    }!
    0.45
     ym
    0.45
    胴
    0.45
    㑯
    0.44
    POSITIVE LOGITS
    ro
    0.51
    ber
    0.50
     EVs
    0.50
    as
    0.49
    block
    0.48
    rats
    0.47
    rang
    0.46
    tae
    0.46
    ug
    0.46
    scored
    0.45
    Activations Density 0.001%

    No Known Activations