© 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. 16-GEMMASCOPE-2-RES-262K
    7. 6703
    Prev
    Next
    INDEX
    Explanations

    places called town

    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_16_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
    d
    1.25
    f
    1.18
    dh
    1.16
    s
    1.15
    of
    1.05
    دي
    1.03
    de
    1.01
    ле
    0.98
    typen
    0.98
    druck
    0.97
    POSITIVE LOGITS
    न
    1.20
     powied
    1.14
    가
    1.14
    야
    1.11
    ন
    1.10
    νει
    1.07
    나
    0.98
    ある
    0.96
     festivities
    0.96
    제
    0.96
    Activations Density 0.199%

    No Known Activations