© 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. 40-GEMMASCOPE-2-RES-262K
    7. 6181
    Prev
    Next
    INDEX
    Explanations

    preference for states or activities

    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_40_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
    Ме
    0.27
     Πε
    0.27
    ¿
    0.27
    敏感
    0.27
    ○
    0.26
    •
    0.25
    iei
    0.25
     ভে
    0.25
    </tr>
    0.25
     Fears
    0.24
    POSITIVE LOGITS
     being
    0.46
     brevity
    0.45
     sendo
    0.41
     putting
    0.39
     giving
    0.38
     spending
    0.37
     siendo
    0.36
     být
    0.36
     seeing
    0.35
     improvisation
    0.35
    Activations Density 0.030%

    No Known Activations