© 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. 73969
    Prev
    Next
    INDEX
    Explanations

    writing and creative process

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

    signaling pathways, died, systems, BI, attack

    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
     I
    0.58
     realm
    0.45
     W
    0.45
     GAS
    0.44
     w
    0.44
     caster
    0.44
     regions
    0.44
     ion
    0.44
    </h2>
    0.43
     kern
    0.43
    POSITIVE LOGITS
    डून
    0.56
     محک
    0.52
     representando
    0.52
    بین
    0.50
    ړئ
    0.50
    بعد
    0.50
    supportsFocus
    0.50
    د
    0.49
    <unused53>
    0.48
    퓰
    0.48
    Activations Density 0.005%

    No Known Activations