© 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. 71127
    Prev
    Next
    INDEX
    Explanations

    account access and password resets

    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
     finally
    0.46
     lastly
    0.46
     thrice
    0.46
     kidneys
    0.44
     കൊണ്ട്
    0.44
     outlined
    0.43
    擰
    0.43
     two
    0.43
     brute
    0.43
     minions
    0.43
    POSITIVE LOGITS
    beweg
    0.45
     região
    0.45
    椷
    0.44
    地区
    0.42
    Title
    0.42
     স্থানীয়
    0.41
    Blurred
    0.41
    标题
    0.41
    asă
    0.41
    City
    0.40
    Activations Density 0.009%

    No Known Activations