© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 123822
    Prev
    Next
    INDEX
    Explanations

    Machine Learning, recipes, tracker

    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
     that
    0.53
    가
    0.48
    omania
    0.48
     blackout
    0.45
    が
    0.45
     of
    0.44
     issuance
    0.44
    1
    0.44
    ꜱ
    0.44
     Ericsson
    0.44
    POSITIVE LOGITS
     Condiciones
    0.47
    إ
    0.47
    !\
    0.46
     conse
    0.44
     souha
    0.42
     (!)
    0.41
    নাথ
    0.40
     지도
    0.40
    }}}=\
    0.40
     Upstairs
    0.39
    Activations Density 0.000%

    No Known Activations