© 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. 134597
    Prev
    Next
    INDEX
    Explanations

    altar, hook, wavelength, ads

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

    companies and their growth

    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
     rozp
    0.46
     feste
    0.46
    겅
    0.44
     cominc
    0.42
    ško
    0.42
     atractivo
    0.42
    EndDate
    0.42
     kore
    0.41
     पृ
    0.41
     Vä
    0.41
    POSITIVE LOGITS
    is
    0.55
    0.53
    /*
    0.51
    /****
    0.50
     principles
    0.49
    och
    0.49
     oct
    0.48
    uar
    0.47
     ions
    0.47
     eukaryotic
    0.46
    Activations Density 0.000%

    No Known Activations