© 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. 13759
    Prev
    Next
    INDEX
    Explanations

    descriptive qualifiers

    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
    .}$
    0.53
     testen
    0.49
     haught
    0.47
     harmonique
    0.47
     Folgen
    0.47
     Ressourcen
    0.46
     nummer
    0.44
     diversité
    0.44
     liberté
    0.44
    utente
    0.44
    POSITIVE LOGITS
    𒐪
    0.39
    ϊ
    0.38
    其他的
    0.38
    ],//
    0.38
    <unused2199>
    0.38
    ainak
    0.37
    undai
    0.37
    ;,
    0.37
    ￠
    0.36
    <unused2121>
    0.36
    Activations Density 0.086%

    No Known Activations