© 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. 1470
    Prev
    Next
    INDEX
    Explanations

    elements followed by specific words

    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
    ли
    0.44
    يط
    0.43
    трибу
    0.43
    و
    0.42
    нде
    0.41
    лийн
    0.41
    лить
    0.40
    倛
    0.40
    씬
    0.40
    лити
    0.39
    POSITIVE LOGITS
    Pp
    0.53
     Defender
    0.48
     Countess
    0.48
     castle
    0.47
    agi
    0.47
     etat
    0.46
     Direktor
    0.46
     katanya
    0.46
    ink
    0.46
     private
    0.46
    Activations Density 0.001%

    No Known Activations