© 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. 4995
    Prev
    Next
    INDEX
    Explanations

    reporting survey results

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

    statements about willingness or perception

    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
     אפ
    0.48
     מ
    0.44
    קס
    0.40
    Datei
    0.39
    בר
    0.39
     fratello
    0.39
     మనం
    0.39
    步伐
    0.38
     א
    0.38
     treason
    0.38
    POSITIVE LOGITS
     respondents
    0.91
     respondent
    0.77
     Respondents
    0.73
     Respondent
    0.64
     perceived
    0.64
     perceptions
    0.57
    Respondent
    0.57
     percib
    0.50
     reported
    0.50
     perceives
    0.49
    Activations Density 0.286%

    No Known Activations