© 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. 29050
    Prev
    Next
    INDEX
    Explanations

    list review scores expansion

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

    daily through demanding of shuttlecock rescue breaths throws the

    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
     eczema
    0.48
    一年
    0.47
    ভ
    0.46
    ↼
    0.45
     ILLINOIS
    0.44
     melamine
    0.41
     invito
    0.41
    带
    0.41
     onyx
    0.41
     convexe
    0.41
    POSITIVE LOGITS
    ാ
    0.54
     बताती
    0.53
    ಾಂಶ
    0.49
    ິດ
    0.46
     कहती
    0.45
    잍
    0.45
     चलता
    0.44
    וק
    0.44
     উঠিল
    0.43
    ਾ
    0.43
    Activations Density 0.000%

    No Known Activations