© 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. 10525
    Prev
    Next
    INDEX
    Explanations

    this menu

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

    multilingual content

    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
     NSMutable
    0.46
    icl
    0.45
     rechts
    0.43
     am
    0.43
    @[+][
    0.43
     thereof
    0.43
    oti
    0.42
     Schuld
    0.41
     marcada
    0.41
     Davies
    0.40
    POSITIVE LOGITS
     යු
    0.46
     düny
    0.43
     подойдет
    0.42
    ualaikum
    0.41
     せ
    0.40
     πο
    0.40
    کان
    0.39
    کن
    0.38
    ungsseite
    0.38
     pover
    0.38
    Activations Density 0.001%

    No Known Activations