© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 6164
    Prev
    Next
    INDEX
    Explanations

    take a [action/decision]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    Overlay
    0.79
    }});
    0.79
     Overlay
    0.78
    Brain
    0.78
    clouds
    0.77
    Attenuation
    0.77
    Implementation
    0.77
     индика
    0.76
    }));
    0.76
    Lack
    0.74
    POSITIVE LOGITS
     advantage
    1.33
     stroll
    1.16
     steps
    1.14
     plunge
    1.13
     stance
    1.13
     precaution
    1.12
     liberties
    1.09
     heed
    1.07
     pains
    1.07
     decisiones
    1.02
    Activations Density 0.023%

    No Known Activations