© 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. 170063
    Prev
    Next
    INDEX
    Explanations

    concrete nouns and hazards

    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
    Ве
    0.51
     therapist
    0.46
     типу
    0.45
     punya
    0.42
    <0xD0>
    0.41
    Це
    0.41
     nutrient
    0.41
     tipo
    0.40
    Ду
    0.39
     therapists
    0.39
    POSITIVE LOGITS
    屇
    0.46
    ㇇
    0.44
     அச்ச
    0.43
     पाल
    0.42
     calles
    0.42
    鋆
    0.42
    䨘
    0.42
     ते
    0.42
    一同
    0.42
    陖
    0.42
    Activations Density 0.007%

    No Known Activations