© 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. 112613
    Prev
    Next
    INDEX
    Explanations

    make your wall art

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

    initially viewed or stories

    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
     dap
    0.43
     рано
    0.43
     Bolívar
    0.43
     sacked
    0.42
     стоимости
    0.42
     요
    0.42
     베
    0.41
     .,
    0.41
     张
    0.41
     tighten
    0.41
    POSITIVE LOGITS
    kem
    0.46
    }//
    0.46
    CRR
    0.46
    esch
    0.45
    літи
    0.45
    gien
    0.45
    al
    0.44
    asn
    0.44
    мини
    0.43
    解決
    0.43
    Activations Density 0.001%

    No Known Activations