© 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. 161849
    Prev
    Next
    INDEX
    Explanations

    foreign language content

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

    desktop application or API

    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
    Dtls
    0.50
    4
    0.48
    偏移
    0.48
    花
    0.44
    params
    0.43
     cardiology
    0.43
    de
    0.43
    7
    0.43
     stabil
    0.42
    不
    0.42
    POSITIVE LOGITS
    掝
    0.53
     ಬರುತ್ತ
    0.51
     서비스를
    0.44
    ან
    0.44
     воск
    0.44
     servizi
    0.44
    хі
    0.42
     ฟรี
    0.42
    ”।
    0.42
     چلے
    0.41
    Activations Density 0.000%

    No Known Activations