© 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. 62103
    Prev
    Next
    INDEX
    Explanations

    prefer cheap

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

    strongly condemn or urge

    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
     unconsciously
    0.55
    蒈
    0.50
     crescimento
    0.48
     automaticamente
    0.46
     рэгістрацыі
    0.46
     যৌগ
    0.46
     Davenport
    0.45
     incess
    0.44
     Umfang
    0.43
     Prozent
    0.43
    POSITIVE LOGITS
    it
    0.66
    ry
    0.59
    ai
    0.55
    us
    0.54
    ij
    0.54
    sm
    0.52
    i
    0.51
    to
    0.51
    next
    0.51
    iller
    0.50
    Activations Density 0.000%

    No Known Activations