© 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. 100968
    Prev
    Next
    INDEX
    Explanations

    Baltic Sea

    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
    نا
    0.44
     sicht
    0.41
    𐰣
    0.41
    ले
    0.41
    shopping
    0.41
    smallest
    0.40
    ता
    0.40
    scientists
    0.40
    翮
    0.39
     chồng
    0.39
    POSITIVE LOGITS
     elektry
    0.51
    بیداری
    0.50
     washout
    0.49
     RTC
    0.49
     OMG
    0.47
    }_{
    0.47
     buurt
    0.47
     RTS
    0.46
     divaricatis
    0.46
     strumenti
    0.46
    Activations Density 0.001%

    No Known Activations