© 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. 227516
    Prev
    Next
    INDEX
    Explanations

    browse through

    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
    नए
    0.44
    ostr
    0.43
    走进
    0.42
     genero
    0.42
    া
    0.42
    o
    0.41
    heroes
    0.41
    ه
    0.41
    ahir
    0.41
    a
    0.40
    POSITIVE LOGITS
     Teal
    0.55
     DVD
    0.53
     VIP
    0.53
     VLAN
    0.52
     contrôle
    0.51
     Kontrolle
    0.51
     Gerade
    0.50
     MAPK
    0.50
    コントロール
    0.49
     HVAC
    0.49
    Activations Density 0.000%

    No Known Activations