© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 15456
    Prev
    Next
    INDEX
    Explanations

    specifying what comes next

    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
    "
    0.46
     Phenomena
    0.41
     phenomena
    0.41
    োয়া
    0.41
     flavours
    0.40
     catered
    0.40
    の影響
    0.39
     flavors
    0.38
    鵡
    0.38
    禳
    0.38
    POSITIVE LOGITS
     einge
    0.54
    ു
    0.52
    ૩
    0.49
    tu
    0.46
    ské
    0.46
    to
    0.45
    sko
    0.45
     בשנת
    0.45
     retainer
    0.44
    tete
    0.44
    Activations Density 0.004%

    No Known Activations