© 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. 191671
    Prev
    Next
    INDEX
    Explanations

    devoted followings

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

    aim, protected, rescue, reservations

    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
    ěli
    0.47
     പ്രേ
    0.45
    扮
    0.45
    urr
    0.45
    ^{(
    0.45
    onent
    0.45
    llr
    0.44
    arrison
    0.43
     පසු
    0.43
     Eintritt
    0.43
    POSITIVE LOGITS
    버
    0.49
     novel
    0.46
    文字列
    0.46
     fermionic
    0.46
    fichier
    0.46
     outliers
    0.46
    ナ
    0.45
    のある
    0.44
     densely
    0.44
    চ
    0.44
    Activations Density 0.000%

    No Known Activations