© 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. 40-GEMMASCOPE-2-RES-262K
    7. 120297
    Prev
    Next
    INDEX
    Explanations

    conversational AI

    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_40_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
    一
    0.47
    ological
    0.46
    cznie
    0.46
    적
    0.45
    韓國
    0.44
    ally
    0.43
    ologically
    0.43
    火
    0.42
    ically
    0.41
    ially
    0.41
    POSITIVE LOGITS
    phabet
    0.44
    terdam
    0.41
    okus
    0.40
    FA
    0.40
    melee
    0.39
    *'
    0.39
    FAC
    0.39
    \,.
    0.39
    echen
    0.39
    [];
    0.38
    Activations Density 0.040%

    No Known Activations