© 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. 3913
    Prev
    Next
    INDEX
    Explanations

    dive into topics

    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
     Auswirkungen
    0.32
     alatt
    0.30
    ínu
    0.29
     Fahrzeuge
    0.27
     estadounidenses
    0.27
     或者
    0.27
    作物
    0.26
    Ｏ
    0.26
    evším
    0.26
     を
    0.26
    POSITIVE LOGITS
     deeper
    0.44
     uncharted
    0.40
     the
    0.37
     গভ
    0.34
     realms
    0.34
     into
    0.34
     depths
    0.32
     profundo
    0.32
     conversations
    0.31
     profunda
    0.31
    Activations Density 0.235%

    No Known Activations