© 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. 5475
    Prev
    Next
    INDEX
    Explanations

    identifying entities and attributes

    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
    痱
    0.49
     svilupp
    0.49
    㴌
    0.48
    剻
    0.47
    ösungen
    0.46
    <unused1086>
    0.46
     എങ്ങനെ
    0.45
    赚
    0.44
     ডেভেলপ
    0.44
    䂘
    0.44
    POSITIVE LOGITS
     mentions
    0.67
     detected
    0.60
     identified
    0.60
     identifies
    0.58
    name
    0.57
     mention
    0.56
    identified
    0.56
     identifiable
    0.56
     identifying
    0.56
     identification
    0.55
    Activations Density 0.512%

    No Known Activations