© 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. 98907
    Prev
    Next
    INDEX
    Explanations

    significantly, ALS, trying, Patterson

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

    animal characteristics

    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
    вак
    0.55
    FreeBuf
    0.53
    čaj
    0.53
    𝘬
    0.53
    Opened
    0.52
    sendBuf
    0.52
    ки
    0.51
     returnPacket
    0.50
     serangan
    0.50
    łac
    0.50
    POSITIVE LOGITS
    a
    0.48
    ↵
    0.47
     hereto
    0.46
    body
    0.44
     quer
    0.44
     Body
    0.44
     theor
    0.43
     Quer
    0.42
     daily
    0.41
     predom
    0.40
    Activations Density 0.000%

    No Known Activations