© 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. 71289
    Prev
    Next
    INDEX
    Explanations

    public forum, app usage, USA inflation, enclosed text

    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
     এর
    0.52
    ai
    0.50
     minions
    0.48
     =\
    0.48
     Cinderella
    0.48
    an
    0.46
     老
    0.44
     agendas
    0.44
     Fortune
    0.44
    ebles
    0.43
    POSITIVE LOGITS
    ט
    0.46
    िट
    0.43
    ισμό
    0.43
    รายละเอียด
    0.43
    Invocation
    0.43
    後來
    0.41
    바
    0.40
    மாக
    0.40
    bier
    0.40
     турында
    0.40
    Activations Density 0.001%

    No Known Activations