© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 160335
    Prev
    Next
    INDEX
    Explanations

    listings banning restrictions

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

    providing multiple versions or options

    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
    getResources
    0.47
    getMax
    0.46
    稃
    0.46
    চৈতন্যের
    0.46
    주고
    0.46
    jaer
    0.45
    ार्थक
    0.45
    隸
    0.45
    퓰
    0.45
    𝐗
    0.45
    POSITIVE LOGITS
     banned
    0.52
     проще
    0.51
     bags
    0.49
    :
    0.48
     gro
    0.47
     banning
    0.47
     listings
    0.46
     come
    0.46
     be
    0.46
     sacks
    0.46
    Activations Density 0.002%

    No Known Activations