© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 44849
    Prev
    Next
    INDEX
    Explanations

    RandomForestClassifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     medzi
    1.47
     avete
    1.34
    ン
    1.24
     aici
    1.23
     liye
    1.21
     terceira
    1.18
     sentado
    1.18
     mye
    1.17
    iendo
    1.16
     neste
    1.16
    POSITIVE LOGITS
    OS
    1.30
    )
    1.11
    RH
    1.10
    NaBH
    1.07
    }
    1.06
    EL
    1.05
    AU
    1.04
    dır
    1.03
    IOR
    1.03
    가지
    0.99
    Activations Density 0.001%

    No Known Activations