© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 6667
    Prev
    Next
    INDEX
    Explanations

    almost always, almost no

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    iation
    0.42
    el
    0.40
    ts
    0.38
    oC
    0.37
    t
    0.36
    taining
    0.35
    tn
    0.35
    se
    0.34
    ti
    0.34
    tau
    0.34
    POSITIVE LOGITS
     understated
    0.41
    }$
    0.39
    ↵
    0.37
     pronounced
    0.36
    펫
    0.36
    ח
    0.35
    ፕሮ
    0.35
     impaired
    0.35
     unlikely
    0.34
     regarded
    0.34
    Activations Density 0.612%

    No Known Activations