© 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-65K
    7. 11823
    Prev
    Next
    INDEX
    Explanations

    lack of function or effectiveness

    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_65k_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
     なる
    0.40
    臺灣
    0.40
    ṇ
    0.39
    aternary
    0.38
    from
    0.37
    STRA
    0.36
     पृष्ठभूमि
    0.36
    ᄉ
    0.36
     வரும்
    0.36
    wl
    0.36
    POSITIVE LOGITS
     useless
    0.93
     pointless
    0.85
     ineffective
    0.85
     meaningless
    0.85
     effectiveness
    0.82
     inutile
    0.79
     worthless
    0.77
     inutil
    0.70
     unusable
    0.65
     Effectiveness
    0.64
    Activations Density 0.214%

    No Known Activations