© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 37148
    Prev
    Next
    INDEX
    Explanations

    further yourself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AssetDiscovery
    0.46
     Ио
    0.45
    ida
    0.42
    ="\
    0.42
    Chief
    0.42
    lica
    0.41
     પારિજા
    0.41
    ẹ
    0.41
    KEYCODE
    0.41
    ﺤ
    0.41
    POSITIVE LOGITS
     superb
    0.45
    マイ
    0.45
     Tracey
    0.44
     atyp
    0.44
     ер
    0.43
     uptime
    0.43
     Livraison
    0.42
     कहें
    0.42
     wow
    0.42
     observables
    0.42
    Activations Density 0.000%

    No Known Activations